Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    proper nouns and numbers in text

    oai_token-act-pair · gpt-3.5-turbo

    references to personal memories or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Miliband
    -0.60
     gard
    -0.58
     Assange
    -0.57
     Fail
    -0.57
     Labour
    -0.57
     aggress
    -0.55
     Tsarnaev
    -0.54
     scapego
    -0.54
     Ukip
    -0.53
     Petraeus
    -0.52
    POSITIVE LOGITS
    zona
    0.73
    çĶ°
    0.66
    Interstitial
    0.61
     respectively
    0.61
     pts
    0.58
    ukemia
    0.56
    Ü
    0.56
    itled
    0.56
    ãĥīãĥ©ãĤ´ãĥ³
    0.56
    ĸļ
    0.54
    Act Density 2.776%

    No Known Activations